Evaluation

Importing libraries

import tensorflow as tf
from tensorflow import keras
import numpy as np
import pandas as pd
from keras.models import load_model
import random
import cv2
import matplotlib.pyplot as plt

SEED=42

print('TensorFlow version:', tf.__version__)

TensorFlow version: 2.10.1

Loading models and data

test_df = pd.read_pickle('../model/iteration_0/test_df.pkl')
print("test data loaded succesfully")

model_path = "../model/iteration_0/cnn_model.h5"
model = load_model(model_path)
print("Model loaded successfully")

test data loaded succesfully
Model loaded successfully

test_df.sample(n=3, random_state=SEED)

	id	image_path	type_landscape	type_mythological	type_portrait	type_religious	label	label_name
294	13340	../data/toy_dataset/13340.jpg	False	False	True	False	2	portrait
454	23395	../data/toy_dataset/23395.jpg	True	False	False	False	0	landscape
584	6767	../data/toy_dataset/6767.jpg	True	False	False	False	0	landscape

The data is correctly loaded, now the model will be loaded

model.summary()

Model: "model_2"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_4 (InputLayer)        [(None, 299, 299, 3)]     0         
                                                                 
 xception (Functional)       (None, 10, 10, 2048)      20861480  
                                                                 
 global_average_pooling2d_2   (None, 2048)             0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dropout_2 (Dropout)         (None, 2048)              0         
                                                                 
 dense_2 (Dense)             (None, 4)                 8196      
                                                                 
=================================================================
Total params: 20,869,676
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_4 (InputLayer)        [(None, 299, 299, 3)]     0         
                                                                 
 xception (Functional)       (None, 10, 10, 2048)      20861480  
                                                                 
 global_average_pooling2d_2   (None, 2048)             0         
 (GlobalAveragePooling2D)                                        
                                                                 
 dropout_2 (Dropout)         (None, 2048)              0         
                                                                 
 dense_2 (Dense)             (None, 4)                 8196      
                                                                 
=================================================================
Total params: 20,869,676
Trainable params: 8,196
Non-trainable params: 20,861,480
_________________________________________________________________

Function to preprocess images

IMG_SIZE = (299, 299)

def parse_image(filename):
    image = tf.io.read_file(filename)
    image = tf.image.decode_jpeg(image, channels=3)
    image = tf.image.resize(image, IMG_SIZE)
    image = keras.applications.xception.preprocess_input(image)
    return image

Create grad-cam

The first step is the get the correcy layer

from IPython.display import display
import matplotlib as mpl
import matplotlib.pyplot as plt
import matplotlib.image as mpimg

model_builder = keras.applications.xception.Xception
img_size = (299, 299)
preprocess_input = keras.applications.xception.preprocess_input
decode_predictions = keras.applications.xception.decode_predictions


row = test_df.sample(1, random_state=SEED).iloc[0]
img_path = row['image_path']
label = row['label']
label_name = row['label_name']

img = mpimg.imread(img_path)
plt.imshow(img)
plt.axis('off')
plt.show()

from keras import Model
# 1) Identify the pooling layer in your trained model:
pooling_layer = model.get_layer("global_average_pooling2d_2")
#    └── its input tensor is the 10×10×2048 conv-feature-map you want.

# 2) Build a new “grad-model” that returns both
#      a) that conv-map, and
#      b) your final predictions
grad_model = Model(
    inputs = model.inputs,
    outputs = [ pooling_layer.input, model.output ]
)

def get_img_array(img_path, size):
    # `img` is a PIL image of size 299x299
    img = keras.utils.load_img(img_path, target_size=size)
    # `array` is a float32 Numpy array of shape (299, 299, 3)
    array = keras.utils.img_to_array(img)
    # We add a dimension to transform our array into a "batch"
    # of size (1, 299, 299, 3)
    array = np.expand_dims(array, axis=0)
    return array


def make_gradcam_heatmap(img_array, grad_model, pred_index=None):
    # Then, we compute the gradient of the top predicted class for our input image
    # with respect to the activations of the last conv layer
    with tf.GradientTape() as tape:
        last_conv_layer_output, preds = grad_model(img_array)
        if pred_index is None:
            pred_index = tf.argmax(preds[0])
        class_channel = preds[:, pred_index]

    # This is the gradient of the output neuron (top predicted or chosen)
    # with regard to the output feature map of the last conv layer
    grads = tape.gradient(class_channel, last_conv_layer_output)

    # This is a vector where each entry is the mean intensity of the gradient
    # over a specific feature map channel
    pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))

    # We multiply each channel in the feature map array
    # by "how important this channel is" with regard to the top predicted class
    # then sum all the channels to obtain the heatmap class activation
    last_conv_layer_output = last_conv_layer_output[0]
    heatmap = last_conv_layer_output @ pooled_grads[..., tf.newaxis]
    heatmap = tf.squeeze(heatmap)

    # For visualization purpose, we will also normalize the heatmap between 0 & 1
    heatmap = tf.maximum(heatmap, 0) / tf.math.reduce_max(heatmap)
    return heatmap.numpy()

img_array = preprocess_input(get_img_array(img_path, size=img_size))

preds = model.predict(img_array)
probs = preds[0]
top_index = np.argmax(probs)
top_confidence = probs[top_index]

print(f"Predicted class index: {top_index}  (confidence {top_confidence:.3f})")

heatmap = make_gradcam_heatmap(img_array, grad_model)

plt.matshow(heatmap)
plt.show()

1/1 [==============================] - 0s 29ms/step
Predicted class index: 2  (confidence 0.869)

def display_gradcam(img_path, heatmap, alpha=0.4):
    # Load the original image
    img = keras.utils.load_img(img_path)
    img = keras.utils.img_to_array(img)

    # Rescale heatmap to a range 0-255
    heatmap = np.uint8(255 * heatmap)

    # Use jet colormap to colorize heatmap
    jet = mpl.colormaps["jet"]

    # Use RGB values of the colormap
    jet_colors = jet(np.arange(256))[:, :3]
    jet_heatmap = jet_colors[heatmap]

    # Create an image with RGB colorized heatmap
    jet_heatmap = keras.utils.array_to_img(jet_heatmap)
    jet_heatmap = jet_heatmap.resize((img.shape[1], img.shape[0]))
    jet_heatmap = keras.utils.img_to_array(jet_heatmap)

    # Superimpose the heatmap on original image
    superimposed_img = jet_heatmap * alpha + img
    superimposed_img = keras.utils.array_to_img(superimposed_img)


    # Display Grad CAM
    display(superimposed_img)


display_gradcam(img_path, heatmap)

pairs = test_df[['label', 'label_name']].drop_duplicates(subset='label')
label_map = pairs.set_index('label')['label_name'].to_dict()

def class_prediction(img_array, label_map, label_name):
    preds = model.predict(img_array)
    probs = preds[0]

    top_index = np.argmax(probs)
    top_confidence = probs[top_index]

    print(f"Predicted class index: {top_index}  (confidence {top_confidence:.3f})")


    print("Predicted class name:", label_map[top_index])
    print("True class name:", label_name)

class_prediction(img_array, label_map, label_name)

1/1 [==============================] - 0s 33ms/step
1/1 [==============================] - 0s 33ms/step
Predicted class index: 2  (confidence 0.869)
Predicted class name: portrait
True class name: portrait

Here it shows clearly that the model focuses on the faces and with this predict the class is portrait

row = test_df.sample(2, random_state=SEED).iloc[1]
img_path = row['image_path']
label = row['label']
label_name = row['label_name']

img_array = preprocess_input(get_img_array(img_path, size=img_size))

heatmap = make_gradcam_heatmap(img_array, grad_model)

plt.matshow(heatmap)
plt.show()

display_gradcam(img_path, heatmap)
class_prediction(img_array, label_map, label_name)

1/1 [==============================] - 0s 28ms/step
1/1 [==============================] - 0s 28ms/step
Predicted class index: 0  (confidence 0.882)
Predicted class name: landscape
True class name: landscape

It is visible that the model is looking in the distance to classify it correctly as a landscape

row = test_df.sample(7, random_state=SEED).iloc[6]
img_path = row['image_path']
label = row['label']
label_name = row['label_name']

img_array = preprocess_input(get_img_array(img_path, size=img_size))

heatmap = make_gradcam_heatmap(img_array, grad_model)

plt.matshow(heatmap)
plt.show()

display_gradcam(img_path, heatmap)
class_prediction(img_array, label_map, label_name)

1/1 [==============================] - 0s 29ms/step
1/1 [==============================] - 0s 29ms/step
Predicted class index: 0  (confidence 0.848)
Predicted class name: landscape
True class name: landscape

Again it is visible that the model is looking in the distance

Next steps

The evaluation is kept short on purpose. The goal was to get the gradcam working and inspect a few images. The model performs surpisingly well on a small amount of test data seen. It looks at the correct places. The next iteration should focus on clustering of the data to see if there is a pattern.